skills/labring/fastgpt/doc-i18n/Gen Agent Trust Hub

doc-i18n

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (git diff --name-only and git diff --cached --name-only) to identify target files for translation.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation files which could contain malicious instructions designed to influence the agent's behavior during the translation process.\n
  • Ingestion points: Markdown content files (.mdx) and navigation configuration files (meta.json) located in the document/content/ directory.\n
  • Boundary markers: Absent. There are no explicit instructions to the agent to disregard natural language commands that may be embedded within the source documentation.\n
  • Capability inventory: The skill possesses the ability to execute shell commands (git diff) and perform file system write operations to create or update .en.mdx and meta.en.json files across the specified directory structure.\n
  • Sanitization: Absent. While the skill defines rules for preserving MDX components and JSON structure, it does not include mechanisms to sanitize or filter the actual text content for potential injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 11:30 AM
Security Audit — agent-trust-hub — doc-i18n